Electronic Proceedings in Theoretical Computer Science · 2014 · 58 citations · 20 references
ComputingComputer ScienceLinguisticsComputational LinguisticsNatural Language ProcessingSemanticsCompositional SemanticsLanguage ModelingLanguage ModelsMeaning RepresentationNatural Language UnderstandingCategorical SemanticsEntanglement GenerationEntanglement StructureLanguage Representation Systems
In both quantum mechanics and corpus linguistics based on vector spaces, the notion of entanglement provides a means for the various subsystems to communicate with each other. In this paper we examine a number of implementations of the categorical framework of Coecke, Sadrzadeh and Clark (2010) for natural language, from an entanglement perspective. Specifically, our goal is to better understand in what way the level of entanglement of the relational tensors (or the lack of it) affects the compositional structures in practical situations. Our findings reveal that a number of proposals for verb construction lead to almost separable tensors, a fact that considerably simplifies the interactions between the words. We examine the ramifications of this fact, and we show that the use of Frobenius algebras mitigates the potential problems to a great extent. Finally, we briefly examine a machine learning method that creates verb tensors exhibiting a sufficient level of entanglement.
20
Introduction to information retrieval
Choice Reviews Online · 2009 · 12.6K citations
Automatic word sense discrimination
Hinrich Schütze · 1998 · 1.3K citations
Composition in Distributional Models of Semantics
Jeff Mitchell, Mirella Lapata · Cognitive Science · 2010 · 981 citations
A categorical semantics of quantum protocols
Samson Abramsky, Bob Coecke · 2004 · 566 citations
Computing, Computer Science, Physics +15